Detecting AutoEncoder is Enough to Catch LDM Generated Images

TL;DR

This paper introduces a detection method for images generated by Latent Diffusion Models that leverages artifacts from their autoencoders, achieving high accuracy without training on generated images.

Contribution

The novel approach detects LDM-generated images by identifying autoencoder artifacts without needing to train on synthetic data, reducing computational costs.

Findings

High detection accuracy achieved

Minimal false positives demonstrated

Effective without training on generated images

Abstract

In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated by Latent Diffusion Models (LDM) by identifying artifacts introduced by their autoencoders. By training a detector to distinguish between real images and those reconstructed by the LDM autoencoder, the method enables detection of generated images without directly training on them. The novelty of this research lies in the fact that, unlike similar approaches, this method does not require training on synthesized data, significantly reducing computational costs and enhancing generalization ability. Experimental results show high detection accuracy with minimal false positives, making this approach a promising tool for combating fake images.